Gen AI/ LLM Engineer

ERM Placement Services; Khordha; On-site; INR 1,200,000 - 1,800,000; Full time

Job summary

ERM Placement Services in Kolkata seeks a GenAI / LLM Engineer with 2–8 years of hands-on Python experience to build scalable AI apps and enterprise workflows.

The role focuses on integrating LLMs, designing RAG pipelines with vector databases, and delivering AI-powered copilots, chatbots, and automation. Collaboration with data, cloud, and product teams is essential.

Qualifications

• Hands-on experience building scalable GenAI apps and enterprise LLM integration.
• Experience with RAG architectures, embeddings, and semantic retrieval.
• Familiarity with prompt engineering and LLM orchestration.

Responsibilities

• Design, develop, and deploy GenAI applications using LLMs and Agentic AI frameworks.
• Build and optimize RAG pipelines with vector databases and embedding models.
• Develop AI-powered chatbots, copilots, assistants, and workflow automation solutions.
• Integrate foundation models such as GPT, Claude, Llama, Gemini into enterprise systems.
• Work on prompt engineering, fine-tuning, evaluation, and model optimization.
• Develop APIs and backend services using Python.
• Collaborate with data engineering, cloud, and product teams for scalable deployments.
• Implement monitoring, guardrails, and performance tuning for GenAI apps.
• Stay updated with GenAI, autonomous agents, and AI tooling ecosystems.

Skills

Python

LLMs

GenAI

RAG

Embeddings

Vector databases

LangChain

Agentic AI

REST APIs

Cloud platforms

Microservices

Tools

LangChain

LangGraph

CrewAI

AutoGen

Semantic Kernel

Pinecone

ChromaDB

FAISS

Weaviate

Milvus

Job description

Job Description GenAI / LLM Engineer

Experience:2–8 Years
Work Locations:Kolkata

We are looking for skilled and passionate GenAI Engineers with strong experience in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), Agentic AI frameworks, and Python development. The ideal candidate should have hands‑on experience building scalable AI applications, integrating LLMs into enterprise workflows, and developing intelligent autonomous systems.

Key Responsibilities

• Design, develop, and deploy GenAI applications using LLMs and Agentic AI frameworks.
• Build and optimize RAG pipelines using vector databases and embedding models.
• Develop AI-powered chatbots, copilots, assistants, and workflow automation solutions.
• Integrate foundation models such as GPT, Claude, Llama, Gemini, or similar into enterprise systems.
• Work on prompt engineering, fine-tuning, evaluation, and model optimization.
• Develop APIs and backend services using Python.
• Collaborate with data engineering, cloud, and product teams for scalable deployments.
• Implement monitoring, guardrails, and performance tuning for GenAI applications.
• Stay updated with advancements in GenAI, autonomous agents, and AI tooling ecosystems.

Required Skills

• Strong hands‑on experience in Pythonprogramming.
• Experience with Large Language Models (LLMs)and GenAI ecosystems.
• Strong understanding of RAG architectures, embeddings, vector search, and semantic retrieval.
• Experience with Agentic AI frameworkssuch as LangChain, LangGraph, CrewAI, AutoGen, Semantic Kernel, or similar.
• Hands‑on experience with vector databases like Pinecone, ChromaDB, FAISS, Weaviate, or Milvus.
• Experience in prompt engineering and LLM orchestration.
• Familiarity with REST APIs, microservices, and cloud platforms.
• Good understanding of AI application deployment and scalability.